-
Avoiding Side Effects in Complex Environments
Reward function specification can be difficult, even in simple environme...
06/11/2020 ∙ by Alexander Matt Turner, et al. ∙
0
∙
share
read it
-
Optimal Farsighted Agents Tend to Seek Power
Some researchers have speculated that capable reinforcement learning (RL...
12/03/2019 ∙ by Alexander Matt Turner, et al. ∙
0
∙
share
read it
-
Conservative Agency via Attainable Utility Preservation
Reward functions are often misspecified. An agent optimizing an incorrec...
02/26/2019 ∙ by Alexander Matt Turner, et al. ∙
0
∙
share
read it
